[PATCH review 8/8] vfs: Test for and handle paths that are unreachable from their mnt_root

[Eric W. Biederman]

In rare cases a directory can be renamed out from under a bind mount.
In those cases without special handling it becomes possible to walk up
the directory tree to the root dentry of the filesystem and down
from the root dentry to every other file or directory on the filesystem.

Like division by zero .. from an unconnected path can not be given
a useful semantic as there is no predicting at which path component
the code will realize it is unconnected.  We certainly can not match
the current behavior as the current behavior is a security hole.

Therefore when encounting .. when following an unconnected path
return -ENOENT.

- Add a function path_connected to verify nd->path.dentry is reachable
  from nd->path.mnt.mnt_root.  AKA to validate that rename did not do
  something nasty to the bind mount.

  To avoid races path_connected must be called after following a path
  component to it's next path component.

Signed-off-by: "Eric W. Biederman" <ebiederm at xmission.com>
---
 fs/namei.c | 26 ++++++++++++++++++++++++--
 1 file changed, 24 insertions(+), 2 deletions(-)

diff --git a/fs/namei.c b/fs/namei.c
index ae4e4c18b2ac..de3549a6c696 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -560,6 +560,23 @@ static int __nd_alloc_stack(struct nameidata *nd)
 	return 0;
 }
 
+/**
+ * path_connected - Verify that a nd->path.dentry is below nd->path.mnt->mnt.mnt_root
+ * @nd: nameidate to verify
+ *
+ * Rename can sometimes move a file or directory outside of a bind
+ * mount, path_connected allows those cases to be detected.
+ */
+static bool path_connected(const struct path *path)
+{
+	struct vfsmount *mnt = path->mnt;
+
+	if (likely(!(mnt->mnt_flags & MNT_DIR_ESCAPED)))
+		return true;
+
+	return is_subdir(path->dentry, mnt->mnt_root);
+}
+
 static inline int nd_alloc_stack(struct nameidata *nd)
 {
 	if (likely(nd->depth != EMBEDDED_LEVELS))
@@ -1296,6 +1313,8 @@ static int follow_dotdot_rcu(struct nameidata *nd)
 				return -ECHILD;
 			nd->path.dentry = parent;
 			nd->seq = seq;
+			if (unlikely(!path_connected(&nd->path)))
+				return -ENOENT;
 			break;
 		} else {
 			struct mount *mnt = real_mount(nd->path.mnt);
@@ -1396,7 +1415,7 @@ static void follow_mount(struct path *path)
 	}
 }
 
-static void follow_dotdot(struct nameidata *nd)
+static int follow_dotdot(struct nameidata *nd)
 {
 	if (!nd->root.mnt)
 		set_root(nd);
@@ -1412,6 +1431,8 @@ static void follow_dotdot(struct nameidata *nd)
 			/* rare case of legitimate dget_parent()... */
 			nd->path.dentry = dget_parent(nd->path.dentry);
 			dput(old);
+			if (unlikely(!path_connected(&nd->path)))
+				return -ENOENT;
 			break;
 		}
 		if (!follow_up(&nd->path))
@@ -1419,6 +1440,7 @@ static void follow_dotdot(struct nameidata *nd)
 	}
 	follow_mount(&nd->path);
 	nd->inode = nd->path.dentry->d_inode;
+	return 0;
 }
 
 /*
@@ -1634,7 +1656,7 @@ static inline int handle_dots(struct nameidata *nd, int type)
 		if (nd->flags & LOOKUP_RCU) {
 			return follow_dotdot_rcu(nd);
 		} else
-			follow_dotdot(nd);
+			return follow_dotdot(nd);
 	}
 	return 0;
 }
-- 
2.2.1